Artificial intelligence in knee osteoarthritis: A comprehensive review for 2022

Correlation of the Radiographic Grading of Knee Osteoarthritis With Physical Function but Not Emotional Quality of Life Scores

Background Multiple studies have shown that symptoms of knee osteoarthritis (OA) weakly correlate with the radiographic severity of the disease. Our objective was to determine possible correlations between the radiographic severity of knee OA and clinical manifestations such as disability, pain scores, and emotional health. Methods A retrospective review of registry data of 305 patients with knee OA was collected. The Kellgren-Lawrence and Ahlbäck classifications of radiographic knee OA were computed. These were correlated with the severity of functional limitations measured using the 36-Item Short-Form Health Survey (SF-36), Knee Society Score (KSS), and Oxford Knee Score (OKS). Statistical analysis was conducted with IBM SPSS Statistics for Windows, Version 22.0 (Released 2013; IBM Corp., Armonk, New York, United States). A p-value of 0.05 or less was considered statistically significant. Results There were no differences in BMI, gender, or operative site between all grades. There were significant differences in KSS Function scores between grade 2/3 patients and grade 4 patients. There were significant differences in OKS and SF-36 Physical Function between grade 2 and grade 4 patients. When comparing the loss of joint space with the functional scores, there were no statistically significant correlations. Conclusion Our study shows that increased radiological severity of knee OA was associated with increased limitation in the ability of patients to carry out their usual physical function. However, there was no significant correlation between radiological findings and non-tangible domains such as mental health, social functioning, and emotional role functions.

The design of a sample rapid magnetic resonance imaging (MRI) acquisition protocol supporting assessment of multiple articular tissues and pathologies in knee osteoarthritis

Objective

This expert opinion paper proposes a design for a state-of-the-art magnetic resonance image (MRI) acquisition protocol for knee osteoarthritis clinical trials in early and advanced disease. Semi-quantitative and quantitative imaging endpoints are supported, partly amendable to automated analysis. Several (peri-) articular tissues and pathologies are covered, including synovitis.

Method

A PubMed literature search was conducted, with focus on the past 5 years. Further, osteoarthritis imaging experts provided input. Specific MRI sequences, orientations, spatial resolutions and parameter settings were identified to align with study goals. We strived for implementation on standard clinical scanner hardware, with a net acquisition time ≤30 ​min.

Results

Short- and long-term longitudinal MRIs should be obtained at ≥1.5T, if possible without hardware changes during the study. We suggest a series of gradient- and spin-echo-sequences, supporting MOAKS, quantitative analysis of cartilage morphology and T2, and non-contrast-enhanced depiction of synovitis. These sequences should be properly aligned and positioned using localizer images. One of the sequences may be repeated in each participant (re-test), optimally at baseline and follow-up, to estimate within-study precision. All images should be checked for quality and protocol-adherence as soon as possible after acquisition. Alternative approaches are suggested that expand on the structural endpoints presented.

Conclusions

We aim to bridge the gap between technical MRI acquisition guides and the wealth of imaging literature, proposing a balance between image acquisition efficiency (time), safety, and technical/methodological diversity. This approach may entertain scientific innovation on tissue structure and composition assessment in clinical trials on disease modification of knee osteoarthritis.

MedKnee: A New Deep Learning-Based Software for Automated Prediction of Radiographic Knee Osteoarthritis

In computer-aided medical diagnosis, deep learning techniques have shown that it is possible to offer performance similar to that of experienced medical specialists in the diagnosis of knee osteoarthritis. In this study, a new deep learning (DL) software, called "MedKnee" is developed to assist physicians in the diagnosis process of knee osteoarthritis according to the Kellgren and Lawrence (KL) score. To accomplish this task, 5000 knee X-ray images obtained from the Osteoarthritis Initiative public dataset (OAI) were divided into train, valid, and test datasets in a ratio of 7:1:2 with a balanced distribution across each KL grade. The pre-trained Xception model is used for transfer learning and then deployed in a Graphical User Interface (GUI) developed with Tkinter and Python. The suggested software was validated on an external public database, Medical Expert, and compared with a rheumatologist's diagnosis on a local database, with the involvement of a radiologist for arbitration. The MedKnee achieved an accuracy of 95.36% when tested on Medical Expert-I and 94.94% on Medical Expert-II. In the local dataset, the developed tool and the rheumatologist agreed on 23 images out of 30 images (74%). The MedKnee's satisfactory performance makes it an effective assistant for doctors in the assessment of knee osteoarthritis.

Epidemiology of osteoarthritis: literature update 2022-2023

PURPOSE OF REVIEW

This review highlights recently published studies on osteoarthritis (OA) epidemiology, including topics related to understudied populations and joints, imaging, and advancements in artificial intelligence (AI) methods.

RECENT FINDINGS

Contemporary research has improved our understanding of the burden of OA in typically understudied regions, including ethnic and racial minorities in high-income countries, the Middle East and North Africa (MENA) and Latin America. Efforts have also been made to explore the burden and risk factors in OA in previously understudied joints, such as the hand, foot, and ankle. Advancements in OA imaging techniques have occurred alongside the developments of AI methods aiming to predict disease phenotypes, progression, and outcomes.

SUMMARY

Continuing efforts to expand our knowledge around OA in understudied populations will allow for the creation of targeted and specific interventions and inform policy changes aimed at reducing disease burden in these groups. The burden and disability associated with OA is notable in understudied joints, warranting further research efforts that may lead to effective therapeutic options. AI methods show promising results of predicting OA phenotypes and progression, which also may encourage the creation of targeted disease modifying OA drugs (DMOADs).

Estimating time-to-total knee replacement on radiographs and MRI: a multimodal approach using self-supervised deep learning

Purpose

Accurately predicting the expected duration of time until total knee replacement (time-to-TKR) is crucial for patient management and health care planning. Predicting when surgery may be needed, especially within shorter windows like 3 years, allows clinicians to plan timely interventions and health care systems to allocate resources more effectively. Existing models lack the precision for such time-based predictions. A survival analysis model for predicting time-to-TKR was developed using features from medical images and clinical measurements.

Methods

From the Osteoarthritis Initiative dataset, all knees with clinical variables, MRI scans, radiographs, and quantitative and semiquantitative assessments from images were identified. This resulted in 895 knees that underwent TKR within the 9-year follow-up period, as specified by the Osteoarthritis Initiative study design, and 786 control knees that did not undergo TKR (right-censored, indicating their status beyond the 9-year follow-up is unknown). These knees were used for model training and testing. Additionally, 518 and 164 subjects from the Multi-Center Osteoarthritis Study and internal hospital data were used for external testing, respectively. Deep learning models were utilized to extract features from radiographs and MR scans. Extracted features, clinical variables, and image assessments were used in survival analysis with Lasso Cox feature selection and a random survival forest model to predict time-to-TKR.

Results

The proposed model exhibited strong discrimination power by integrating self-supervised deep learning features with clinical variables (eg, age, body mass index, pain score) and image assessment measurements (eg, Kellgren-Lawrence grade, joint space narrowing, bone marrow lesion size, cartilage morphology) from multiple modalities. The model achieved an area under the curve of 94.5 (95% CI, 94.0-95.1) for predicting the time-to-TKR.

Conclusions

The proposed model demonstrated the potential of self-supervised learning and multimodal data fusion in accurately predicting time-to-TKR that may assist physicians to develop personalize treatment strategies.